Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc34b779669ac664537d405202e60d4c4bf74ba69f23a278bff1710c7ff69392
+oid sha256:a7cb3e037bdce69674d876090e02534850f44fdc8760524a13123cc446ee8775
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef316a2427ed9f06bf60371ff6402a618ce78c0a4452e5aaa88d3811a3dedfd2
+oid sha256:98b7aabe82568b7119f483097ec00f50abdc4295d673c0a79af791281e7e06a0
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508bf57c0b7938cf6320eb2547b85198a04772745c43c070dc89ffb1a83ebce8
+oid sha256:1d63f7a496bcd2565d401f276d2feed4b5c2a5d1160a87b647230fc7a7b03806
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13495782567947517,
+  "epoch": 0.16869728209934395,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 34.709,
       "eval_steps_per_second": 4.397,
       "step": 36
+    },
+    {
+      "epoch": 0.14620431115276475,
+      "grad_norm": 0.1827002316713333,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 1.889,
+      "step": 39
+    },
+    {
+      "epoch": 0.15745079662605435,
+      "grad_norm": 0.23876498639583588,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 2.0144,
+      "step": 42
+    },
+    {
+      "epoch": 0.16869728209934395,
+      "grad_norm": 0.22354301810264587,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 1.9035,
+      "step": 45
+    },
+    {
+      "epoch": 0.16869728209934395,
+      "eval_loss": 1.9489043951034546,
+      "eval_runtime": 12.9724,
+      "eval_samples_per_second": 34.689,
+      "eval_steps_per_second": 4.394,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1768647705952256e+16,
+  "total_flos": 1.4730824339423232e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null